Cross-Area Transfer Learning for VLC-based Indoor Localization with a Transfer Efficiency Score

Masood Jan; Wafa Njima; Xun Zhang; Alexander Artemenko

cs.LGOct 21, 2026

Cross-Area Transfer Learning for VLC-based Indoor Localization with a Transfer Efficiency Score

Authors: Masood Jan, Wafa Njima, Xun Zhang, Alexander Artemenko

Organizations: Doctoral School of Computer Science, Telecommunications and Electronics (EDITE), Sorbonne University, 75006 Paris, France · LISITE Laboratory, Institut Supérieur d’Électronique de Paris, 75006 Paris, France · Université Paris-Saclay, LISV Laboratory, France · sector research of Robert Bosch GmbH in Stuttgart, Germany

Abstract

Indoor localization systems are critical for Industry-4.0 applications. Visible Light Communication (VLC)-based systems offer advantages such as immunity to electromagnetic interference, high accuracy, and energy efficiency, but their performance is hindered by environmental variability across deployment areas. This paper presents a transfer learning (TL) framework for VLC-based indoor localization that enhances cross-area robustness while reducing data requirements. Using real-world measurements from four distinct areas of a Bosch manufacturing facility, we show that fine-tuning a deep neural network (DNN) pre-trained on source area data with only 40% of target-area measurements recovers 97% of full-data performance, thereby reducing the amount of target data needed. We further introduce the Transfer Efficiency Score (TES), a composite metric that identifies the most effective source models for transfer without exhaustive evaluation. Guided by TES, the framework selects the best source model, yielding localization errors as low as 40.9 cm with success rates above 86%. Validation on an unseen area confirms its generalization capability, with a 3.28 cm mean error achieved using the TES-selected source model. Overall, the proposed framework provides a scalable and data-efficient pathway for industrial VLC localization, substantially reducing deployment costs and computational burden while maintaining high accuracy in diverse and dynamic environments.

Figures & tables

Fig. 2 : Workflow of the proposed TL framework with TES assessment and validation.

Fig. 3 : Architecture of the implemented VLC transceiver.

Power Supply
Supply voltage	12 V
Supply current	1.2 A
Power supply interface	USB-C female
Tx
Driving current signal range	200 mA $\pm$ 100 mA
Transmitted optical power range	500 mW $\pm$ 250 mW

TABLE I : VLC Transceiver Specifications.

Fig. 5 : Composite picture from the Tx towards the measurement area in the industry hall at BOSCH in Blaichach.

Panel of Figure 7 — Fig. 6 : (a) Tx/Rx setup. (b) Floor plan layout of the measurement area.

Panel of Table 8 — TABLE II : 3D coordinates, placement context, and deployment areas of transmitters.

Parameter	Description	Value
Optimizer	Model optimizer	ADAM
Learning rate, $\eta$	Step size in gradient descent	0.0001
Batch size, $B$	Number of samples per batch	64
Epochs per iteration, $E$	Number of training epochs	1000
Input dimension, $d$	Size of input feature vector	10
Hidden layers, $L$	Number of hidden layers	5

TABLE III : TL Simulation Settings

Panel of Figure 10 — Fig. 7 : TL performance evaluation across different validation areas before and after TL: (a) Area A localization error, (b) Area A success rate, (c) Area B localization error, (d) Area B success rate, (e) Area C localization error, and (f) Area C success rate.

Source	Metric	Train (Source)	Val. (Source)	Target 1 (Before/After TL)		Target 2 (Before/After TL)
				Before	After	Before	After
Area A	Error (cm)	57.73	57.74	134.91 (B)	40.90 (B)	101.08 (C)	51.55 (C)
Area A	Success (%)	84.47	80	23.66 (B)	86.02 (B)	30.68 (C)	98.48 (C)
Area B	Error (cm)	32.09	39.57	91.04 (A)	67.20 (A)	69.70 (C)	51.88 (C)
Area B	Success (%)	95.84	90.32	37.05 (A)	97.19 (A)	59.09 (C)	98.24 (C)
Area C	Error (cm)	48.22	50.58	121.28 (A)	63.88 (A)	153.66 (B)	43.09 (B)

TABLE IV : TL results on different areas and metrics. A/B/C in parentheses denote the respective target area.

Transfer	SR @0.5 m	SR @1.0 m	SR @1.5 m	SR @2.0 m
A $\to$ B	78%	86%	96%	100%
A $\to$ C	77%	98%	100%	100%
B $\to$ A	81%	97%	100%	100%
B $\to$ C	79%	98%	100%	100%
C $\to$ A	61%	82%	96%	100%
C $\to$ B	76%	91%	97%	100%

TABLE V : Success rate sensitivity to distance threshold

\delta

across all source–target transfers.

Panel of Figure 13 — Fig. 8 : Localization error and success rate trends for representative TL scenarios across different fine-tuning data ratios: (a) A $\rightarrow$ B localization error, (b) A $\rightarrow$ C localization error, (c) A $\rightarrow$ B success rate, and (d) A $\rightarrow$ C success rate.

Data %	Error (cm)						Success (%)
Data %	A $\to$ B	A $\to$ C	B $\to$ A	B $\to$ C	C $\to$ A	C $\to$ B	A $\to$ B	A $\to$ C	B $\to$ A	B $\to$ C	C $\to$ A	C $\to$ B
10	47.34	53.93	71.4	58.14	68.84	46.89	75.63	96.97	93.68	97.35	87.02	92.47
20	44.43	53.22	70.07	54.46	66.2	45.04	81.36	96.97	95.79	98.11	86.67	92.47
40	40.90	51.55	67.2	51.88	63.87	43.09	86.02	98.48	96.84	99.11	85.96	93.55
60	40.53	51.06	66.58	51.35	63.6	42.16	87.46	98.48	97.19	99.36	87.37	93.91
100	40.01	50.26	63.89	51.18	61.74	41.14	88.17	98.86	98.95	99.62	87.37	94.62

TABLE VI : Localization error (cm) and success rate (%) for all six source–target transfer scenarios across five fine-tuning data ratios.

Panel of Figure 15 — Fig. 9 : Comparison of TES-selected and baseline models on unseen Area D: (a) localization error and (b) success rate.

Source→Target	Post-TL Metrics		Normalized Values		TES	Avg. TES (per source area)
Source→Target	Error (cm)	Success (%)	NE	NSR	TES	Avg. TES (per source area)
A $\to$ B	40.90	86.02	0.0000	0.2537	0.6269	0.7132
A $\to$ C	51.55	98.48	0.4008	1.0000	0.7996	0.7132
B $\to$ A	67.20	97.19	1.0000	0.9215	0.4607	0.6224
B $\to$ C	51.88	98.24	0.4186	0.9869	0.7841	0.6224
C $\to$ A	63.88	81.78	0.8857	0.0000	0.0572	0.3876

TABLE VII : TES results for all source–target pairs, showing post-TL metrics, normalized values, and computed TES.

$\alpha$	Avg TES (A)	Avg TES (B)	Avg TES (C)	Best Source
0.30	0.679	0.755	0.336	B
0.40	0.696	0.688	0.362	A $\approx$ B
0.50	0.713	0.622	0.388	A
0.60	0.731	0.556	0.414	A
0.70	0.748	0.490	0.439	A

TABLE VIII : TES sensitivity to the weighting parameter

\alpha

Area Pair	Bhattacharyya Distance ( $D_{B}$ )	Bidirectional Avg. TES
A–B	0.137	0.544
A–C	0.213	0.428
B–C	0.107	0.751

TABLE IX : Bhattacharyya Distance vs. Bidirectional Avg. TES.

Panel of Figure 19 — Fig. 10 : Comparison of partial and full fine-tuning for representative transfers to Area A under different target-data ratios: (a) B $\rightarrow$ A transfer and (b) C $\rightarrow$ A transfer.

Wireless Localization

Wireless localization uses radio signals and sensor fusion to estimate the positions and trajectories of people, devices, and transmitters.

See all 65 papers

A Transfer Learning-Driven Methodology for Efficient and Sustainable Indoor Localization Using VLC
Oct 21, 2026Masood Jan, Wafa Njima, Xun Zhang +1Wireless Localization Transfer Learning
Doctoral School of Computer Science, Telecommunications and Electronics (EDITE), Sorbonne University, Paris, France · LISITE Laboratory, Institut Supérieur d’Électronique de Paris, Paris, France · Université Paris-Saclay, LISV Laboratory, France +1
Deep Attention-based Sequential Ensemble Learning for BLE-Based Indoor Localization in Care Facilities
Mar 22, 2026Minh Triet Pham, Quynh Chi Dang, Le Nhat TanWireless Localization Ensemble Learning
School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia · Faculty of Applied Science, Ho Chi Minh City University of Technology, Vietnam National University - Ho Chi Minh City, Ho Chi Minh City, Vietnam
Radiance-Field Guided Pretraining: Scaling Localization Models with Unlabeled Wireless Signals
Dec 8, 2025Guosheng Wang, Shen Wang, Lei YangSelf-Supervised Pre-Training Wireless Localization
Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China

Oct 21, 2026J/K move · Enter open · S save

A Transfer Learning-Driven Methodology for Efficient and Sustainable Indoor Localization Using VLC

Masood Jan, Wafa Njima, Xun Zhang, Alexander Artemenko

Doctoral School of Computer Science, Telecommunications and Electronics (EDITE), Sorbonne University, Paris, France · LISITE Laboratory, Institut Supérieur d’Électronique de Paris, Paris, France · Université Paris-Saclay, LISV Laboratory, France+1

Wireless Localization Transfer Learning Energy-Efficient ML

Open paper AskPDF arXiv

The rapid expansion of the Internet of Things enables seamless collaboration among connected devices, making indoor localization a critical component of industrial automation. However, conventional localization techniques struggle in dynamic environments. These methods depend on extensive, frequent data collection and environment-specific calibration, limiting scalability, interoperability, and effective use of prior research while imposing significant energy penalties that hinder practical deployment. To address these challenges, we propose an energy-efficient transfer learning (TL) based approach for visible light communication based indoor localization. Our method leverages TL to tackle environmental variability, including lighting fluctuations and physical obstacles that typically degrade localization performance, while simultaneously reducing computational overhead and energy consumption compared to conventional approaches. We also introduce a novel model efficiency (ME) metric, designed to integrate localization accuracy, energy efficiency, data efficiency, and transfer gain into a single evaluative measure for comprehensive optimization. Evaluations on a real-world dataset collected from a BOSCH factory demonstrate that our model achieves a 47% improvement in localization accuracy compared to a conventional model that does not utilize TL, and achieves up to 67.5% ME with TL models, compared to only 10.4% in conventional models under high-noise conditions. These results underscore the potential of our approach to deliver a highly efficient and scalable indoor localization system suitable for energy-constrained industrial applications.

Abstract

Wireless Localization

Explore similar work

A Transfer Learning-Driven Methodology for Efficient and Sustainable Indoor Localization Using VLC

Deep Attention-based Sequential Ensemble Learning for BLE-Based Indoor Localization in Care Facilities

Radiance-Field Guided Pretraining: Scaling Localization Models with Unlabeled Wireless Signals